Wei Yao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wei Yao has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Cheng Lian
Wuhan University of Technology
4 shared publications - Huiming Tang
Faculty of Engineering, China University of Geosciences, Wuhan, China
4 shared publications - Zhigang Zeng
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, Hubei, CHINA
4 shared publications - Cheng Lian
School of Chemistry and Molecular Engineering, East China University of Science and Technology, Shanghai, 200237, China
2 shared publications - Li Cheng
South-Central Minzu University
2 shared publications - Lorenzo Bruzzone
Department of Information Engineering and Computer Science, University of Trento, Trento, Italy
2 shared publications
Latest Publications
- Open Access
- 18 June 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (12) , 2032
A Dual-Branch Detector Based on the Multi-Granularity Dynamic Selection Mechanism for Remote Sensing Incremental Detection
In practical remote sensing object detection tasks, the application of deep learning approaches often takes the form of incremental learning: when the application includes new target types that were not encountered during training, a pre-trained model must acquire new knowledge without suffering catastrophic forgetting. Among the various techniques proposed, knowledge distillation (KD)-based regularization has proven to be one of the most effective methods. Current KD-based approaches primarily focus on addressing inter-task confusion and optimizing feature selection during distillation processes. In this paper, we propose a dual-branch detector-independent learning framework and a multi-granularity dynamic selection strategy. The former decouples detection tasks for old and new classes to mitigate inter-class confusion, while the latter is a novel, exquisitely designed distillation mechanism that ensures precise transfer of critical old-class information. Moreover, we apply a DIST loss that aligns both inter-class and intra-class relations, further enhancing the fidelity of old-class knowledge transfer. Experiments on the DIOR and DOTA datasets demonstrate that our method significantly outperforms state-of-the-art incremental-learning approaches for remote-sensing object detection and exhibits good robustness under different remote-sensing scenarios.
- 18 June 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (12) , 2032
Open AccessA Dual-Branch Detector Based on the Multi-Granularity Dynamic Selection Mechanism for Remote Sensing Incremental Detection
In practical remote sensing object detection tasks, the application of deep learning approaches often takes the form of incremental learning: when the application includes new target types that were not encountered during training, a pre-trained model must acquire new knowledge without suffering catastrophic forgetting. Among the various techniques proposed, knowledge distillation (KD)-based regularization has proven to be one of the most effective methods. Current KD-based approaches primarily focus on addressing inter-task confusion and optimizing feature selection during distillation processes. In this paper, we propose a dual-branch detector-independent learning framework and a multi-granularity dynamic selection strategy. The former decouples detection tasks for old and new classes to mitigate inter-class confusion, while the latter is a novel, exquisitely designed distillation mechanism that ensures precise transfer of critical old-class information. Moreover, we apply a DIST loss that aligns both inter-class and intra-class relations, further enhancing the fidelity of old-class knowledge transfer. Experiments on the DIOR and DOTA datasets demonstrate that our method significantly outperforms state-of-the-art incremental-learning approaches for remote-sensing object detection and exhibits good robustness under different remote-sensing scenarios.
- Open Access
- 25 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 16663-16679
Fine-Grained Style Alignment and Class Balance for Unsupervised Domain Adaptation in Remote Sensing Image Segmentation
Unsupervised Domain Adaptation (UDA) is an effective method for addressing the domain shift issue between the source and target domains in high-resolution (HR) remote sensing images (RSIs) classification. However, existing methods still face significant challenges when dealing with substantial style discrepancies and class imbalance. For instance, the widely used Adaptive Instance Normalization (AdaIN) method reduces the distribution difference by transforming the style of source domain images to match that of the target domain. However, when confronted with large style variations, this method often leads to the loss of fine-grained details such as color, texture, and contrast, negatively impacting the transfer performance of the model. Additionally, class imbalance causes the model to be biased towards dominant classes, resulting in decreased overall classification accuracy. To address these issues, this paper proposes two innovative modules. First, we introduce the SelfAdaIN module, which precisely controls the style transformation process through an adaptive convolutional generation mechanism. This module effectively prevents the loss of fine details found in traditional AdaIN methods, achieving fine-grained style alignment between the source and target domains. Secondly, we propose a Class Balance Loss (CBL) function that adjusts the weight distribution of target domain samples to mitigate the influence of dominant classes and enhance the focus on rare categories, thereby alleviating the issue of class imbalance. Extensive experiments on four cross-domain remote sensing datasets demonstrate that the proposed methods significantly improve classification accuracy. Code is available at https://github.com/nclab-1/FGSA-CB
- 25 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 16663-16679
Open AccessFine-Grained Style Alignment and Class Balance for Unsupervised Domain Adaptation in Remote Sensing Image Segmentation
Unsupervised Domain Adaptation (UDA) is an effective method for addressing the domain shift issue between the source and target domains in high-resolution (HR) remote sensing images (RSIs) classification. However, existing methods still face significant challenges when dealing with substantial style discrepancies and class imbalance. For instance, the widely used Adaptive Instance Normalization (AdaIN) method reduces the distribution difference by transforming the style of source domain images to match that of the target domain. However, when confronted with large style variations, this method often leads to the loss of fine-grained details such as color, texture, and contrast, negatively impacting the transfer performance of the model. Additionally, class imbalance causes the model to be biased towards dominant classes, resulting in decreased overall classification accuracy. To address these issues, this paper proposes two innovative modules. First, we introduce the SelfAdaIN module, which precisely controls the style transformation process through an adaptive convolutional generation mechanism. This module effectively prevents the loss of fine details found in traditional AdaIN methods, achieving fine-grained style alignment between the source and target domains. Secondly, we propose a Class Balance Loss (CBL) function that adjusts the weight distribution of target domain samples to mitigate the influence of dominant classes and enhance the focus on rare categories, thereby alleviating the issue of class imbalance. Extensive experiments on four cross-domain remote sensing datasets demonstrate that the proposed methods significantly improve classification accuracy. Code is available at https://github.com/nclab-1/FGSA-CB
- 26 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-11
Online Compression of Multichannel Power Waveform Data in Distribution Grid With Novel Tensor Method
Power waveform data (PWD) provide detailed and important information for the smart grid. This paper proposes a tensor method to alleviate the stress of multichannel PWD recording significantly.The multichannel PWD is modeled as a high order time incremental tensor which is compressed by a novel method developed on CANDECOMP/PARAFAC (CP) methods. With a completely new principle, the multichannel PWD can be compressed simultaneously, which can raise the compression efficiency significantly. Moreover, for PWD compression, smooth changes of PWD can be compressed at high accuracy with a low memory cost. The new method is able to record various kinds of PWD disturbances such as harmonics, interharmonics, flicker, transients, decay and bias with a large compression ratio, small recover error and moderate computation complexity. The theory, experiments in low voltage distribution grid and medium voltage distribution grid and comparisons with related works validate the values and advantages of the new method for compression of multichannel PWD in distribution grid.
- 26 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-11
Online Compression of Multichannel Power Waveform Data in Distribution Grid With Novel Tensor Method
Power waveform data (PWD) provide detailed and important information for the smart grid. This paper proposes a tensor method to alleviate the stress of multichannel PWD recording significantly.The multichannel PWD is modeled as a high order time incremental tensor which is compressed by a novel method developed on CANDECOMP/PARAFAC (CP) methods. With a completely new principle, the multichannel PWD can be compressed simultaneously, which can raise the compression efficiency significantly. Moreover, for PWD compression, smooth changes of PWD can be compressed at high accuracy with a low memory cost. The new method is able to record various kinds of PWD disturbances such as harmonics, interharmonics, flicker, transients, decay and bias with a large compression ratio, small recover error and moderate computation complexity. The theory, experiments in low voltage distribution grid and medium voltage distribution grid and comparisons with related works validate the values and advantages of the new method for compression of multichannel PWD in distribution grid.
- 2 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20 (1545598X) , 1-5
CS2DT: Cross Spatial–Spectral Dense Transformer for Hyperspectral Image Classification
Compared with general optical images, hyperspectral images (HSIs) contain richer spectral information. On one hand, this provides a sufficient basis for ground object recognition. On the other hand, it results in the intermingling of spatial and spectral information. In order to make better use of the rich spatial and spectral information in HSIs, we resort to Vision Transformer (ViT). To be specific, we propose the Cross Spatial–Spectral Dense Transformer (CS2DT) for spatial-spectral feature extracting and feature fusing. For feature extraction, CS2DT employs the Adaptive Dense Encoder (ADE) module, which enables the extraction of multi-scale semantic information. During the features fusion stage, we use the Cross Spatial–Spectral Attention (CS2A) module based on the cross-attention (CA) operation to better integrate spatial and spectral features. We evaluate the classification performance of the proposed CS2DT on three well-known datasets by conducting extensive experiments. Experimental results demonstrate that CS2DT can achieve higher accuracy and higher stability when compared with the state-of-the-art (SOTA) methods. The source code will be made available at https://github.com/shouhengx/CS2DT.
- 2 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20 (1545598X) , 1-5
CS2DT: Cross Spatial–Spectral Dense Transformer for Hyperspectral Image Classification
Compared with general optical images, hyperspectral images (HSIs) contain richer spectral information. On one hand, this provides a sufficient basis for ground object recognition. On the other hand, it results in the intermingling of spatial and spectral information. In order to make better use of the rich spatial and spectral information in HSIs, we resort to Vision Transformer (ViT). To be specific, we propose the Cross Spatial–Spectral Dense Transformer (CS2DT) for spatial-spectral feature extracting and feature fusing. For feature extraction, CS2DT employs the Adaptive Dense Encoder (ADE) module, which enables the extraction of multi-scale semantic information. During the features fusion stage, we use the Cross Spatial–Spectral Attention (CS2A) module based on the cross-attention (CA) operation to better integrate spatial and spectral features. We evaluate the classification performance of the proposed CS2DT on three well-known datasets by conducting extensive experiments. Experimental results demonstrate that CS2DT can achieve higher accuracy and higher stability when compared with the state-of-the-art (SOTA) methods. The source code will be made available at https://github.com/shouhengx/CS2DT.
- Open Access
- 23 September 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (19) , 4668
SCDA: A Style and Content Domain Adaptive Semantic Segmentation Method for Remote Sensing Images
Due to the differences in imaging methods and acquisition areas, remote sensing datasets can exhibit significant variations in both image style and content. In addition, the ground objects can be quite different in scale even within the same remote sensing image. These differences should be considered in remote sensing image segmentation tasks. Inspired by the recently developed domain generalization model WildNet, we propose a domain adaption framework named “Style and Content Domain Adaptation” (SCDA) for semantic segmentation tasks involving multiple remote sensing datasets with different data distributions. SCDA uses residual style feature transfer (RSFT) in the shallow layer of the baseline network model to enable source domain images to obtain style features from the target domain and reduce the loss of source domain content information. Considering the scale difference of different ground objects in remote sensing images, SCDA uses the projection of the source domain images, the style-transferred source domain images, and the target domain images to construct a multiscale content adaptation learning (MCAL) loss. This enables the model to capture multiscale target domain content information. Experiments show that the proposed method has obvious domain adaptability in remote sensing image segmentation. When performing cross-domain segmentation tasks from VaihingenIRRG to PotsdamIRRG, mIOU is , and the F1 is , marking improvements of and , respectively, compared with state-of-the-art methods. When performing cross-domain segmentation tasks from VaihingenIRRG to PotsdamRGB, the mIOU is , an improvement of over the most advanced methods. In summary, SCDA improves the semantic segmentation of remote sensing images through domain adaptation for both style and content. It fully utilizes multiple innovative modules and strategies to enhance the performance and the stability of the model.- 23 September 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (19) , 4668
Open AccessSCDA: A Style and Content Domain Adaptive Semantic Segmentation Method for Remote Sensing Images
Due to the differences in imaging methods and acquisition areas, remote sensing datasets can exhibit significant variations in both image style and content. In addition, the ground objects can be quite different in scale even within the same remote sensing image. These differences should be considered in remote sensing image segmentation tasks. Inspired by the recently developed domain generalization model WildNet, we propose a domain adaption framework named “Style and Content Domain Adaptation” (SCDA) for semantic segmentation tasks involving multiple remote sensing datasets with different data distributions. SCDA uses residual style feature transfer (RSFT) in the shallow layer of the baseline network model to enable source domain images to obtain style features from the target domain and reduce the loss of source domain content information. Considering the scale difference of different ground objects in remote sensing images, SCDA uses the projection of the source domain images, the style-transferred source domain images, and the target domain images to construct a multiscale content adaptation learning (MCAL) loss. This enables the model to capture multiscale target domain content information. Experiments show that the proposed method has obvious domain adaptability in remote sensing image segmentation. When performing cross-domain segmentation tasks from VaihingenIRRG to PotsdamIRRG, mIOU is , and the F1 is , marking improvements of and , respectively, compared with state-of-the-art methods. When performing cross-domain segmentation tasks from VaihingenIRRG to PotsdamRGB, the mIOU is , an improvement of over the most advanced methods. In summary, SCDA improves the semantic segmentation of remote sensing images through domain adaptation for both style and content. It fully utilizes multiple innovative modules and strategies to enhance the performance and the stability of the model. - Open Access
- 7 October 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (19) , 4982
A CNN Ensemble Based on a Spectral Feature Refining Module for Hyperspectral Image Classification
In the study of hyperspectral image classification based on machine learning theory and techniques, the problems related to the high dimensionality of the images and the scarcity of training samples are widely discussed as two main issues that limit the performance of the data-driven classifiers. These two issues are closely interrelated, but are usually addressed separately. In our study, we try to kill two birds with one stone by constructing an ensemble of lightweight base models embedded with spectral feature refining modules. The spectral feature refining module is a technique based on the mechanism of channel attention. This technique can not only perform dimensionality reduction, but also provide diversity within the ensemble. The proposed ensemble can provide state-of-the-art performance when the training samples are quite limited. Specifically, using only a total of 200 samples from each of the four popular benchmark data sets (Indian Pines, Salinas, Pavia University and Kennedy Space Center), we achieved overall accuracies of 89.34%, 95.75%, 93.58%, and 98.14%, respectively.
- 7 October 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (19) , 4982
Open AccessA CNN Ensemble Based on a Spectral Feature Refining Module for Hyperspectral Image Classification
In the study of hyperspectral image classification based on machine learning theory and techniques, the problems related to the high dimensionality of the images and the scarcity of training samples are widely discussed as two main issues that limit the performance of the data-driven classifiers. These two issues are closely interrelated, but are usually addressed separately. In our study, we try to kill two birds with one stone by constructing an ensemble of lightweight base models embedded with spectral feature refining modules. The spectral feature refining module is a technique based on the mechanism of channel attention. This technique can not only perform dimensionality reduction, but also provide diversity within the ensemble. The proposed ensemble can provide state-of-the-art performance when the training samples are quite limited. Specifically, using only a total of 200 samples from each of the four popular benchmark data sets (Indian Pines, Salinas, Pavia University and Kennedy Space Center), we achieved overall accuracies of 89.34%, 95.75%, 93.58%, and 98.14%, respectively.
- 12 January 2022
- Published by Springer Nature in Natural Hazards
- Vol. 112 (1) , 725-745
Selective ensemble deep bidirectional RVFLN for landslide displacement prediction
- 12 January 2022
- Published by Springer Nature in Natural Hazards
- Vol. 112 (1) , 725-745
Selective ensemble deep bidirectional RVFLN for landslide displacement prediction
- Open Access
- 25 March 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (7) , 1248
Multiple Spectral Resolution 3D Convolutional Neural Network for Hyperspectral Image Classification
In recent years, benefiting from the rapid development of deep learning technology in the field of computer vision, the study of hyperspectral image (HSI) classification has also made great progress. However, compared with ordinary RGB images, HSIs are more like 3D cubes; therefore, it is necessary and beneficial to explore classification methods suitable for the very special data structure of HSIs. In this paper, we propose Multiple Spectral Resolution 3D Convolutional Neural Network (MSR-3DCNN) for HSI classification tasks. In MSR-3DCNN, we expand the idea of multi-scale feature fusion and dilated convolution from the spatial dimension to the spectral dimension, and combine 3D convolution and residual connection; therefore, it can better adapt to the 3D cubic form of hyperspectral data and make efficient use of spectral information in different bands. Experimental results on four benchmark datasets show the effectiveness of the proposed approach and its superiority as compared with some state-of-the-art (SOTA) HSI classification methods.
- 25 March 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (7) , 1248
Open AccessMultiple Spectral Resolution 3D Convolutional Neural Network for Hyperspectral Image Classification
In recent years, benefiting from the rapid development of deep learning technology in the field of computer vision, the study of hyperspectral image (HSI) classification has also made great progress. However, compared with ordinary RGB images, HSIs are more like 3D cubes; therefore, it is necessary and beneficial to explore classification methods suitable for the very special data structure of HSIs. In this paper, we propose Multiple Spectral Resolution 3D Convolutional Neural Network (MSR-3DCNN) for HSI classification tasks. In MSR-3DCNN, we expand the idea of multi-scale feature fusion and dilated convolution from the spatial dimension to the spectral dimension, and combine 3D convolution and residual connection; therefore, it can better adapt to the 3D cubic form of hyperspectral data and make efficient use of spectral information in different bands. Experimental results on four benchmark datasets show the effectiveness of the proposed approach and its superiority as compared with some state-of-the-art (SOTA) HSI classification methods.
- 1 October 2020
- Published by Elsevier in Neural Networks
- Vol. 130, 286-296
Landslide displacement interval prediction using lower upper bound estimation method with pre-trained random vector functional link network initialization
- 1 October 2020
- Published by Elsevier in Neural Networks
- Vol. 130, 286-296
Landslide displacement interval prediction using lower upper bound estimation method with pre-trained random vector functional link network initialization
- 30 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 18 (11) , 1991-1995
ClusterCNN: Clustering-Based Feature Learning for Hyperspectral Image Classification
Convolutional neural networks (CNNs) are widely used in the field of remote sensing images. However, the applications of CNNs and related techniques often ignore the properties of remote sensing data. In our study, we focus on the hyperspectral image (HSI) classification problem, and address the issue of including the very rich spectral information present in HSIs in CNN-based models to produce highly accurate classification results. We propose a two-step classification technique, ClusterCNN. The first step divides HSI pixels into different clusters, to form a material map which can be considered as a compressed expression of the original spectral features. The second step trains a CNN that can extract spatial features from the material map, and then exploits these spatial features to classify HSI pixels. The proposed approach follows a strict hierarchy to exploit both the spectral and spatial features in HSIs. Experimental results show the effectiveness of ClusterCNN as compared to the much more complicated state-of-the-art approaches.
- 30 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 18 (11) , 1991-1995
ClusterCNN: Clustering-Based Feature Learning for Hyperspectral Image Classification
Convolutional neural networks (CNNs) are widely used in the field of remote sensing images. However, the applications of CNNs and related techniques often ignore the properties of remote sensing data. In our study, we focus on the hyperspectral image (HSI) classification problem, and address the issue of including the very rich spectral information present in HSIs in CNN-based models to produce highly accurate classification results. We propose a two-step classification technique, ClusterCNN. The first step divides HSI pixels into different clusters, to form a material map which can be considered as a compressed expression of the original spectral features. The second step trains a CNN that can extract spatial features from the material map, and then exploits these spatial features to classify HSI pixels. The proposed approach follows a strict hierarchy to exploit both the spectral and spatial features in HSIs. Experimental results show the effectiveness of ClusterCNN as compared to the much more complicated state-of-the-art approaches.